Verbalizing Multi-Token Concepts in LLMs

arXiv:2608.31084 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-09-28

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Frozen model — 18× in this paper · explained in 3 episodes
• Calibration — 3× in this paper · explained in 9 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Steering — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 2× in this paper · explained in 3 episodes
• Activation Addition — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 5 episodes
• Conference on Computational Natural Language Learning — 1× in this paper
• Empirical Methods in Natural Language Processing — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• In International Conference on Learning Representations — 1× in this paper
• Interpretability — 1× in this paper · explained in 15 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper

Sources

• Understanding intermediate layers using linear classifier probes
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• Steering Language Models With Activation Engineering

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering